© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 22
    Prev
    Next
    INDEX
    Explanations

    names of people with titles and the context of deaths or memorials

    oai_token-act-pair · gemini-2.0-flash

    Titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.69
    ulemon
    -0.65
     EconPapers
    -0.61
     lenker
    -0.60
     esternos
    -0.60
    UrlResolution
    -0.59
    NUMX
    -0.58
     rehab
    -0.56
    bleshooting
    -0.54
    nastics
    -0.54
    POSITIVE LOGITS
    GEBURTSDATUM
    0.60
    RegressionTest
    0.50
     استنادى
    0.48
     Grenville
    0.45
    ंदीखरीदारी
    0.43
    substack
    0.43
    Ông
    0.42
     Granville
    0.40
     quantités
    0.39
     Langdon
    0.39
    Activations Density 6.199%

    No Known Activations